EDA buscas

O objeto principal da análise são as buscas e a navegação depois da busca. Criamos esses dados a partir dos dados originais da wikimedia em /data/search_data.csv.

Aqui, exploramos esses dados.

library(tidyverse)

package 㤼㸱tidyverse㤼㸲 was built under R version 3.4.4-- Attaching packages --------------------------------------- tidyverse 1.2.1 --
v ggplot2 2.2.1     v purrr   0.2.4
v tibble  1.4.2     v dplyr   0.7.4
v tidyr   0.7.2     v stringr 1.2.0
v readr   1.1.1     v forcats 0.2.0
package 㤼㸱ggplot2㤼㸲 was built under R version 3.4.4package 㤼㸱tibble㤼㸲 was built under R version 3.4.4-- Conflicts ------------------------------------------ tidyverse_conflicts() --
x dplyr::filter() masks stats::filter()
x dplyr::lag()    masks stats::lag()

library(here)

package 㤼㸱here㤼㸲 was built under R version 3.4.4here() starts at C:/Users/marcosasn/Documents/gitlocal/lab2-cp4-marcosasn

library(lubridate)

Attaching package: 㤼㸱lubridate㤼㸲

The following object is masked from 㤼㸱package:here㤼㸲:

    here

The following object is masked from 㤼㸱package:base㤼㸲:

    date

library(shiny)
library(plotly)

Attaching package: 㤼㸱plotly㤼㸲

The following object is masked from 㤼㸱package:ggplot2㤼㸲:

    last_plot

The following object is masked from 㤼㸱package:stats㤼㸲:

    filter

The following object is masked from 㤼㸱package:graphics㤼㸲:

    layout

theme_set(theme_bw())

buscas = read_csv(here::here("data/search_data.csv")) %>%
    head(100000)

Parsed with column specification:
cols(
  session_id = col_character(),
  search_index = col_integer(),
  session_start_timestamp = col_double(),
  session_start_date = col_datetime(format = ""),
  group = col_character(),
  results = col_integer(),
  num_clicks = col_integer(),
  first_click = col_integer()
)

buscas %>% 
    ggplot(aes(x = results)) + 
    geom_histogram(binwidth = 5) 

#search_index quantidade de buscas na sessão
#What is our daily overall clickthrough rate? How does it vary between the groups?
#num_clicks
#group
#session_start_date
plot = buscas %>% 
    group_by(group) %>% 
    summarise(n = n()) %>% 
    ggplot(aes(x = group, y = n)) + 
    geom_col(
        aes(text = paste("Grupo:", group,
                         "<br>",
                         "Frequência:", n)),
        fill = "white", color = "blue") +
    ggtitle("Distribuição da frequência do grupo da sessão") +
    xlab("Grupo") + 
    ylab("Frequência") +
  theme(plot.title = element_text(hjust = 0.5), legend.position="none")

Ignoring unknown aesthetics: text

div(ggplotly(plot, tooltip = "text", width = 700, height = 400),  align = "center")

We recommend that you use the dev version of ggplot2 with `ggplotly()`
Install it with: `devtools::install_github('hadley/ggplot2')`

plot = buscas %>% 
    ggplot(aes(x = group, y = num_clicks)) + 
    geom_jitter(aes(text = paste("Grupo:",group,
                                 "<br>Quantidade índices da busca:",search_index)),
                alpha = .4, width = .2, size = .8, color = "blue") +
    ggtitle("Distribuição da quantidade de índices da busca") +
    xlab("Grupo") + 
    ylab("Quantidade índices da busca") +
  theme(plot.title = element_text(hjust = 0.5), legend.position="none")

Ignoring unknown aesthetics: text

div(ggplotly(plot, tooltip = "text", width = 700, height = 400),  align = "center")

We recommend that you use the dev version of ggplot2 with `ggplotly()`
Install it with: `devtools::install_github('hadley/ggplot2')`

plot = buscas %>% 
    ggplot(aes(x = group, y = num_clicks)) + 
    geom_jitter(aes(text = paste("Grupo:",group,
                                 "<br>Quantidade índices da busca:",search_index)),
                alpha = .4, width = .2, size = .8, color = "blue") +
    scale_y_log10() +
    ggtitle("Distribuição da quantidade de índices da busca") +
    xlab("Grupo") + 
    ylab("Quantidade índices da busca") +
  theme(plot.title = element_text(hjust = 0.5), legend.position="none")

Ignoring unknown aesthetics: text

div(ggplotly(plot, tooltip = "text", width = 700, height = 400),  align = "center")

We recommend that you use the dev version of ggplot2 with `ggplotly()`
Install it with: `devtools::install_github('hadley/ggplot2')`
Transformation introduced infinite values in continuous y-axis

plot = buscas %>% 
    ggplot(aes(x= num_clicks)) + 
    geom_histogram(binwidth = 5, fill = "white", color = "blue") + 
    facet_grid(group ~ .) +
    ggtitle("Distribuição da frequência da quantidade de índices da busca") +
    xlab("Quantidade índices da busca") + 
    ylab("Frequência") +
  theme(plot.title = element_text(hjust = 0.5), legend.position="none")
div(ggplotly(plot, tooltip = "text", width = 700, height = 400),  align = "center")

We recommend that you use the dev version of ggplot2 with `ggplotly()`
Install it with: `devtools::install_github('hadley/ggplot2')`